Identification of people using multiple types of input

Abstract

Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

What is claimed is: 
     
       1. A method, comprising:
 identifying a pool of features from multiple types of input, the pool of features comprising a first video feature from a video input, the first video feature comprising a parent rectangle within a feature rectangle in an image of the video input; 
 calculating a numeric value associated with the first video feature by summing values of pixels in the parent rectangle; 
 generating a classifier for speaker detection using a learning algorithm wherein nodes of the classifier are selected using the pool of features, based on the numeric value associated with the first video feature; 
 dividing an image of a second video feature into a plurality of detection windows; 
 evaluating the classifier against input data for each detection window to produce an estimate of likelihood that a person exists in the detection window; and 
 detecting a person in a region in the image by selecting a region that includes a relatively high number of detection windows that each have a high estimate of likelihood of containing a person. 
 
     
     
       2. The method of  claim 1 , comprising:
 evaluating all of the nodes of the classifier against the input data to produce the estimate of likelihood. 
 
     
     
       3. The method of  claim 1 , comprising:
 stopping the evaluating of the nodes of the classifier before all nodes are evaluated when an already calculated result from the evaluated nodes provides a level of certainty that a particular detection window either does or does not contain a person. 
 
     
     
       4. The method of  claim 1 , comprising:
 excluding a sub-region of input data from consideration for person detection. 
 
     
     
       5. The method of  claim 4 , comprising:
 excluding a sub-region from inclusion in a detection window. 
 
     
     
       6. The method of  claim 5 , comprising:
 excluding a sub-region that includes a display, a projection screen, or a television from inclusion in a detection window. 
 
     
     
       7. An apparatus, comprising a detector device including a detector configured to accept multiple types of input, the multiple types of input comprising a video input, the detector configured to evaluate a person detection classifier to detect a person, the person detection classifier created by:
 identifying a pool of features from multiple types of input, the pool of features comprising a first video feature from a video input, the first video feature comprising a parent rectangle within a feature rectangle in an image of the video input; 
 calculating a numeric value associated with the first video feature by summing values of pixels in the parent rectangle; 
 generating the classifier for person detection using a learning algorithm wherein nodes of the classifier are selected using the pool of features, based on the numeric value associated with the first video feature; 
 dividing an image of a second video feature into a plurality of detection windows; 
 evaluating the classifier against input data for each detection window to produce an estimate of likelihood that a person exists in the detection window; and 
 detecting a person in a region in the image by selecting a region that includes a relatively high number of detection windows that each have a high estimate of likelihood of containing a person. 
 
     
     
       8. The apparatus of  claim 7 , the creation of the person detection classifier comprising:
 evaluating all of the nodes of the classifier against the input data to produce the estimate of likelihood. 
 
     
     
       9. The apparatus of  claim 7 , the creation of the person detection classifier comprising:
 stopping the evaluating of the nodes of the classifier before all nodes are evaluated when an already calculated result from the evaluated nodes provides a level of certainty that a particular detection window either does or does not contain a person. 
 
     
     
       10. The apparatus of  claim 7 , creation of the person detection classifier comprising:
 excluding a sub-region of input data from consideration for person detection. 
 
     
     
       11. The apparatus of  claim 10 , creation of the person detection classifier comprising:
 excluding a sub-region from inclusion in a detection window. 
 
     
     
       12. The apparatus of  claim 11 , creation of the person detection classifier comprising:
 excluding a sub-region that includes a display, a projection screen, or a television from inclusion in a detection window. 
 
     
     
       13. A computer-readable storage medium containing instructions that when executed cause one or more processors to:
 identify a pool of features from multiple types of input, the pool of features comprising a first video feature from a video input, the first video feature comprising a parent rectangle within a feature rectangle in an image of the video input; 
 calculate a numeric value associated with the first video feature by summing values of pixels in the parent rectangle; 
 generate a classifier for speaker detection using a learning algorithm wherein nodes of the classifier are selected using the pool of features, based on the numeric value associated with the first video feature; 
 divide an image of a second video feature into a plurality of detection windows; 
 evaluate the classifier against input data for each detection window to produce an estimate of likelihood that a person exists in the detection window; and 
 detect a person in a region in the image by selecting a region that includes a relatively high number of detection windows that each have a high estimate of likelihood of containing a person. 
 
     
     
       14. The computer-readable storage medium of  claim 13 , containing instructions that when executed cause one or more processors to:
 evaluate all of the nodes of the classifier against the input data to produce the estimate of likelihood. 
 
     
     
       15. The computer-readable storage medium of  claim 13 , containing instructions that when executed cause one or more processors to:
 stop the evaluating of the nodes of the classifier before all nodes are evaluated when an already calculated result from the evaluated nodes provides a level of certainty that a particular detection window either does or does not contain a person. 
 
     
     
       16. The computer-readable storage medium of  claim 13 , containing instructions that when executed cause one or more processors to:
 exclude a sub-region of input data from consideration for person detection. 
 
     
     
       17. The computer-readable storage medium of  claim 16 , containing instructions that when executed cause one or more processors to:
 exclude a sub-region from inclusion in a detection window. 
 
     
     
       18. The computer-readable storage medium of  claim 17 , containing instructions that when executed cause one or more processors to:
 exclude a sub-region that includes a display, a projection screen, or a television from inclusion in a detection window.